## AI GENERATED IMAGE DETECTION

### Problem Statement
With the advent of generative AI, it has become easily difficult to separate real data from AI-Generated.
The goal is to develop a model that can identify a fake photo created by AI.

### Motivation
With the rise of generative AI, fake identities can be easily created using sophisticated algorithms. This has led to an increase in identity fraud, as fake identities can be used to gain access to online services and commit fraudulent activities. Thus, the purpose is to contribute to the development of more secure and reliable online services for everyone.

### Solution
Implement a predictive model that embibes the knowledge of AI-Generated images, and uses them to predict the label of a random image at test time.

### Timeline
**Week 1: `May 22 2023 - May 28 2023`**

* Understand concepts related to the problem statement:
* **CNN based models**: ResNet, VGGNet etc.
* **Transformer architectures**: Vanila attention model and Vision Transformers.

**Week 2: `May 29 2023 - June 5 2023`**
* Download the dataset, get familiarised with the datatypes and attributes.
* Preprocess the data using techniques such as feature reduction.
* Use a predictive model to use the combined feature knowledge to predict the final class.
* Implement a pipeline putting all the elements together and run your code for a few epochs.

**Week 3: `June 6 2023 - June 12 2023`**
* Experiment using different models and their combinations, as well as by tuning their hyperparameters.
* Analyse accuracy metrics with graphs and write a conclusion reporting the qualitative and quantitative results.

This is just a tentative timeline, you are free to move at your own pace.

### Resources
* [Introduction to PyTorch](https://www.dataquest.io/blog/pytorch-for-beginners/)
* [Basics of Deep Learning](https://github.com/vlgiitr/DL_Topics)
* [Overview of Techniques](https://jonathan-hui.medium.com/detect-ai-generated-images-deepfakes-part-4-5f9ae1dfeb13)
* [Vision transformers](https://www.v7labs.com/blog/vision-transformer-guide)
* [CNN Architecture](https://medium.com/analytics-vidhya/cnns-architectures-lenet-alexnet-vgg-googlenet-resnet-and-more-666091488df5)
* [Dataset](https://bitgrit.net/competition/18?ref=mlcontests)
*Please create an account on bitgrit.net, and participate in the challenge to view the dataset